You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
If you call neural_ode with save_start=false it still returns the start. I believe this needed to be overridden internally to get adjoint to work, but what is returned should respect this argument.
It is very common to run these solves only requiring the output to be saved. It would be nice if there was an option like save_only in this case would be the end of the timespan.
The text was updated successfully, but these errors were encountered:
Tested here: https://github.com/jessebett/DiffEqFlux.jl/blob/master/test/solver_options.jl
If you call
neural_ode
withsave_start=false
it still returns the start. I believe this needed to be overridden internally to get adjoint to work, but what is returned should respect this argument.It is very common to run these solves only requiring the output to be saved. It would be nice if there was an option like
save_only
in this case would be the end of the timespan.The text was updated successfully, but these errors were encountered: